© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 28497
    Prev
    Next
    INDEX
    Explanations

    mentions of historical events and their societal impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    letic
    -0.14
    amo
    -0.14
     rowspan
    -0.14
    odal
    -0.14
    анÑģ
    -0.14
     Offensive
    -0.14
     Modular
    -0.14
    utzt
    -0.13
    åĿĢ
    -0.13
    isan
    -0.13
    POSITIVE LOGITS
     medicine
    0.32
     commerce
    0.27
     religion
    0.27
     technology
    0.26
    merce
    0.25
     art
    0.24
     science
    0.23
     finance
    0.23
     pop
    0.23
     media
    0.22
    Activations Density 0.218%

    No Known Activations